© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 4298
    Prev
    Next
    INDEX
    Explanations

    configuration elements and parameters related to plugins and security settings in programming or web development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ataka
    -0.06
    aper
    -0.06
    606
    -0.06
     Haupt
    -0.06
    Programming
    -0.06
    /train
    -0.06
    ijkstra
    -0.06
    PCS
    -0.05
     APIs
    -0.05
    LETTE
    -0.05
    POSITIVE LOGITS
     plugin
    0.13
     plug
    0.12
    PLUGIN
    0.11
    plugin
    0.11
     æı
    0.10
    -plugin
    0.10
     Plugin
    0.10
    Plugin
    0.10
     plugins
    0.09
    æıĴ
    0.09
    Activations Density 0.104%

    No Known Activations